pyxllib 0.3.128__tar.gz → 0.3.130__tar.gz

pyxllib-0.3.130/PKG-INFO

@@ -0,0 +1,86 @@
+Metadata-Version: 2.1
+Name: pyxllib
+Version: 0.3.130
+Summary: 厦门理工模式识别团队通用python代码工具库
+Home-page: https://github.com/XLPRUtils/pyxllib
+Author: code4101
+Author-email: 877362867@qq.com
+License: Apache License 2.0
+Keywords: pyxllib,pyxlpr
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: Programming Language :: Python :: 3
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.6
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: arrow
+Requires-Dist: charset-normalizer
+Requires-Dist: requests
+Requires-Dist: qiniu
+Requires-Dist: pyyaml
+Requires-Dist: loguru
+Requires-Dist: humanfriendly
+Requires-Dist: tqdm
+Requires-Dist: ujson
+Requires-Dist: Deprecated
+Requires-Dist: pyperclip
+Requires-Dist: envariable
+Requires-Dist: decorator
+Requires-Dist: more-itertools
+Requires-Dist: fire
+Requires-Dist: xlrd
+Requires-Dist: pympler
+Requires-Dist: lxml
+Requires-Dist: beautifulsoup4
+Requires-Dist: numpy
+Requires-Dist: Jinja2
+Requires-Dist: pandas>=0.23.4
+Requires-Dist: pillow
+Provides-Extra: xlcv
+Requires-Dist: opencv-python; extra == "xlcv"
+Requires-Dist: pillow; extra == "xlcv"
+Requires-Dist: opsdroid-get-image-size; extra == "xlcv"
+Provides-Extra: xlai
+Requires-Dist: opsdroid-get-image-size; extra == "xlai"
+Requires-Dist: pynvml; extra == "xlai"
+Requires-Dist: opencv-python; extra == "xlai"
+Requires-Dist: visdom; extra == "xlai"
+Requires-Dist: pillow; extra == "xlai"
+Provides-Extra: xlall
+Requires-Dist: xlrd; extra == "xlall"
+Requires-Dist: html2text; extra == "xlall"
+Requires-Dist: flask-restful; extra == "xlall"
+Requires-Dist: opsdroid-get-image-size; extra == "xlall"
+Requires-Dist: flask-jwt-extended; extra == "xlall"
+Requires-Dist: flask; extra == "xlall"
+Requires-Dist: ujson; extra == "xlall"
+Requires-Dist: arts; extra == "xlall"
+Requires-Dist: flask-wtf; extra == "xlall"
+Requires-Dist: opencv-python; extra == "xlall"
+Requires-Dist: sentencepiece; extra == "xlall"
+Requires-Dist: openai2; extra == "xlall"
+Requires-Dist: fastapi; extra == "xlall"
+Requires-Dist: zhconv; extra == "xlall"
+Requires-Dist: pillow; extra == "xlall"
+Requires-Dist: uvicorn; extra == "xlall"
+Requires-Dist: flask-cors; extra == "xlall"
+
+# 1 install
+
+```
+pip install pyxllib
+```
+
+more details: https://www.yuque.com/xlpr/pyxllib/install
+
+# 2 document
+
+document: https://www.yuque.com/xlpr/pyxllib.
+Work hard to improve, welcome more assistant partners.
+
+# 3 Acknowledge
+
+This project uses PyCharm to develop.
+Thanks to [JetBrains'](https://www.jetbrains.com/?from=pyxllib) support
+of [free license for open sourse project development](https://pycharm.iswbm.com/c01/c01_05.html).

{pyxllib-0.3.128 → pyxllib-0.3.130}/pyxllib/algo/intervals.py

@@ -883,7 +883,7 @@ class StrIdxBack:
         self.keystr = s
 
     def delchars(self, pattern, flags=0):
-        """模仿正则的替换语法
+        r""" 模仿正则的替换语法
         但是不用输入替换目标s，以及目标格式，因为都是删除操作
 
         利用正则可以知道被删除的是哪个区间范围

{pyxllib-0.3.128 → pyxllib-0.3.130}/pyxllib/algo/newbie.py

@@ -164,3 +164,57 @@ def cvsecs(time):
         return time
 
     return sum(mult * part for mult, part in zip(factors, reversed(time)))
+
+
+def find_optimal_page_size(total_items, page_sizes, seen_items=0):
+    """
+    找到最优的分页大小，使得最后一页的新样本数尽可能多，已见样本数尽可能少。
+    本函数由gpt-o1生成。
+
+    :param int total_items: 总的条目数（样本数）。
+    :param List[int] page_sizes: 可供选择的分页大小列表。
+    :param int seen_items: 已经看过的样本数，默认为0。
+    :return: Tuple[int, int, int], 包含最优的分页大小、最后一页的新样本数、最后一页的已见样本数。
+
+    >>> find_optimal_page_size(64, [2, 5, 10, 14, 20, 50, 100])
+    (100, 64, 0)
+    >>> find_optimal_page_size(64, [2, 5, 10, 14, 20, 50, 100], seen_items=55)
+    (50, 9, 5)
+    """
+    page_sizes = sorted(set(page_sizes), reverse=True)  # 去重并从大到小排序
+    max_new_items = -1
+    min_seen_items_in_page = total_items + 1  # 初始化为一个大于可能的最大值
+    optimal_page_size = None
+    total_new_items = total_items - seen_items  # 总的新样本数
+
+    for page_size in page_sizes:
+        if page_size <= 0:
+            continue  # 跳过非正整数的分页大小
+
+        total_pages = -(-total_items // page_size)  # 等价于 math.ceil(total_items / page_size)
+        start_index = (total_pages - 1) * page_size + 1
+        end_index = min(total_pages * page_size, total_items)
+        last_page_indices = range(start_index, end_index + 1)
+
+        # 计算新样本数和已见样本数
+        new_items_in_page = len([i for i in last_page_indices if i > seen_items])
+        seen_items_in_page = len([i for i in last_page_indices if i <= seen_items])
+
+        # 更新最优分页大小
+        if new_items_in_page > max_new_items:
+            max_new_items = new_items_in_page
+            min_seen_items_in_page = seen_items_in_page
+            optimal_page_size = page_size
+            # 如果已达到最大可能的新样本数且已见样本数为 0，提前退出
+            if max_new_items == total_new_items and min_seen_items_in_page == 0:
+                break
+        elif new_items_in_page == max_new_items and seen_items_in_page < min_seen_items_in_page:
+            min_seen_items_in_page = seen_items_in_page
+            optimal_page_size = page_size
+            if min_seen_items_in_page == 0:
+                break
+        # 如果当前的 page_size 已经小于或等于最大新样本数，后续的 page_size 不会有更好的结果，可以退出循环
+        elif page_size <= max_new_items:
+            break
+
+    return optimal_page_size, max_new_items, min_seen_items_in_page

{pyxllib-0.3.128 → pyxllib-0.3.130}/pyxllib/data/pglib.py

@@ -781,27 +781,30 @@ class XlprDb(Connection):
         def pretty_val(v):
             return round_int(v) if v > 100 else round(v, 2)
 
-        chart = Line()
-        chart.set_title(title)
-        chart.options['xAxis'][0].update({'min': ls[0][0], 'type': 'time',
-                                          # 'minInterval': 3600 * 1000 * 24,
-                                          'name': '时间', 'nameGap': 50, 'nameLocation': 'middle'})
-        chart.options['yAxis'][0].update({'name': yaxis_name, 'nameGap': 50, 'nameLocation': 'middle'})
-        # 目前是比较暴力的方法调整排版，后续要研究是不是能更自动灵活些
-        chart.options['legend'][0].update({'top': '6%', 'icon': 'pin'})
-        chart.options['grid'] = [{'top': 55 + len(all_users_usaged) * 4, 'containLabel': True}]
-        chart.options['tooltip'].opts.update({'axisPointer': {'type': 'cross'}, 'trigger': 'item'})
-
-        chart.add_series(f'total{pretty_val(ls[0][1]):g}', to_list([x[1] for x in ls]), areaStyle={})
-        for user, usaged in all_users_usaged.most_common():
-            usaged = usaged / ((ls[-1][0] - ls[0][0]).total_seconds() / 3600 + 1e-9)
-            chart.add_series(f'{user}{pretty_val(usaged):g}',
-                             to_list([x[2].get(user, 0) for x in ls]),
-                             areaStyle={}, stack='Total', emphasis={'focus': 'series'})
-
-        return '<body>' + chart.render_embed() + '</body>', sum(all_users_usaged.values())
-
-#   cdx_edit    
+        try:
+            chart = Line()
+            chart.set_title(title)
+            chart.options['xAxis'][0].update({'min': ls[0][0], 'type': 'time',
+                                              # 'minInterval': 3600 * 1000 * 24,
+                                              'name': '时间', 'nameGap': 50, 'nameLocation': 'middle'})
+            chart.options['yAxis'][0].update({'name': yaxis_name, 'nameGap': 50, 'nameLocation': 'middle'})
+            # 目前是比较暴力的方法调整排版，后续要研究是不是能更自动灵活些
+            chart.options['legend'][0].update({'top': '6%', 'icon': 'pin'})
+            chart.options['grid'] = [{'top': 55 + len(all_users_usaged) * 4, 'containLabel': True}]
+            chart.options['tooltip'].opts.update({'axisPointer': {'type': 'cross'}, 'trigger': 'item'})
+
+            chart.add_series(f'total{pretty_val(ls[0][1]):g}', to_list([x[1] for x in ls]), areaStyle={})
+            for user, usaged in all_users_usaged.most_common():
+                usaged = usaged / ((ls[-1][0] - ls[0][0]).total_seconds() / 3600 + 1e-9)
+                chart.add_series(f'{user}{pretty_val(usaged):g}',
+                                 to_list([x[2].get(user, 0) for x in ls]),
+                                 areaStyle={}, stack='Total', emphasis={'focus': 'series'})
+
+            return '<body>' + chart.render_embed() + '</body>', sum(all_users_usaged.values())
+        except Exception as e:
+            return str(e), 0
+
+    #   cdx_edit
     def _get_database_trace_total(self, title, yaxis_name, date_trunc, recent, link_name):
         ls = self.execute(textwrap.dedent(f"""\
             WITH cte1 AS(
@@ -817,7 +820,6 @@ class XlprDb(Connection):
             ORDER BY ttime"""), ((utc_now(8) - recent).isoformat(timespec='seconds'),)).fetchall()
         return self.database_create_stack_chart(title, ls, yaxis_name=yaxis_name)
 
-
     def _get_database_trace_per_host(self, db, title, yaxis_name, date_trunc, recent, link_name):
         ls = self.execute(textwrap.dedent(f"""\
             WITH cte1 AS (
@@ -860,20 +862,20 @@ class XlprDb(Connection):
                 if k == '_total':
                     continue
                 all_database_usaged[k] += v * hours
-    
+
         for i, x in enumerate(ls):
             ct = Counter()
             for k, v in x[1].items():
                 ct[k] += v
             ls[i] = (x[0], ct, int(x[2]))
-    
+
         # 2 转图表可视化
         def to_list(values):
             return [(x[0], v) for x, v in zip(ls, values)]
-    
+
         def pretty_val(v):
             return round_int(v) if v > 100 else round(v, 2)
-    
+
         chart = Line()
         chart.set_title(title)
         chart.options['xAxis'][0].update({'min': ls[0][0], 'type': 'time',
@@ -882,51 +884,52 @@ class XlprDb(Connection):
         chart.options['yAxis'][0].update({'name': yaxis_name, 'nameGap': 50, 'nameLocation': 'middle'})
         # 目前是比较暴力的方法调整排版，后续要研究是不是能更自动灵活些
         chart.options['legend'][0].update({'top': '6%', 'icon': 'pin'})
-        chart.options['grid'] = [{'top': 55 + len(all_database_usaged) * 4 , 'containLabel': True}]
+        chart.options['grid'] = [{'top': 55 + len(all_database_usaged) * 4, 'containLabel': True}]
         chart.options['tooltip'].opts.update({'axisPointer': {'type': 'cross'}, 'trigger': 'item'})
-    
-        chart.add_series(f'total {pretty_val(ls[0][2]/1024/1024/1024):g}', to_list([x[2]/1024/1024/1024 for x in ls]), areaStyle={})
+
+        #chart.add_series(f'total {pretty_val(ls[0][2] / 1024 / 1024 / 1024):g}',
+        #                 to_list([x[2] / 1024 / 1024 / 1024 for x in ls]), areaStyle={})
         for database, usaged in all_database_usaged.most_common():
             usaged = usaged / ((ls[-1][0] - ls[0][0]).total_seconds() / 3600 + 1e-9)
-            chart.add_series(f'{database} {pretty_val(usaged/1024/1024/1024):g}',
-                             to_list([x[1].get(database, 0)/1024/1024/1024 for x in ls]),
+            chart.add_series(f'{database} {pretty_val(usaged / 1024 / 1024 / 1024):g}',
+                             to_list([x[1].get(database, 0) / 1024 / 1024 / 1024 for x in ls]),
                              areaStyle={}, stack='Total', emphasis={'focus': 'series'})
         return '<body>' + chart.render_embed() + '</body>'
 
-    def dbview_xldb1_memory(self,recent=datetime.timedelta(days=30), date_trunc='hour'):
+    def dbview_xldb1_memory(self, recent=datetime.timedelta(days=180), date_trunc='day'):
         from pyxllib.data.echarts import render_echart_html
-        
-        db_list = ['st', 'xlpr', 'stdata', 'kq5034', 'ckz']
+
+        db_list = ['stdata', 'xlpr', 'st', 'ckz']
         args = ['数据库大小(GB)', date_trunc, recent, 'xldb1']
         htmltexts = []
 
-        res = self._get_database_trace_total('XLDB1数据库使用近况', *args)
+        res = self._get_database_trace_total('xldb1数据库使用近况', *args)
         htmltexts.append(res)
 
         data_stats = []
-        for idx,db in enumerate(db_list,start=1):
-            data_stats.append(self._get_database_trace_per_host(db,f'{db}', *args))
+        for idx, db in enumerate(db_list, start=1):
+            data_stats.append(self._get_database_trace_per_host(db, f'{db}', *args))
         htmltexts += data_stats
 
         self.commit()
         h = render_echart_html('database_cdx', body='<br/>'.join(htmltexts))
         return h
-        
-    def dbview_xldb2_memory(self, recent=datetime.timedelta(days=30), date_trunc='hour'):
+
+    def dbview_xldb2_memory(self, recent=datetime.timedelta(days=180), date_trunc='day'):
         from pyxllib.data.echarts import render_echart_html
-    
-        db_list = ['st', 'ragdata']
+
+        db_list = ['ragdata', 'kq5034']
         args = ['数据库大小(GB)', date_trunc, recent, 'xldb2']
         htmltexts = []
-    
-        res = self._get_database_trace_total('XLDB2数据库使用近况', *args)
+
+        res = self._get_database_trace_total('xldb2数据库使用近况', *args)
         htmltexts.append(res)
-    
+
         data_stats = []
         for idx, db in enumerate(db_list, start=1):
             data_stats.append(self._get_database_trace_per_host(db, f'{db}', *args))
         htmltexts += data_stats
-    
+
         self.commit()
         h = render_echart_html('database_cdx', body='<br/>'.join(htmltexts))
         return h
@@ -977,7 +980,7 @@ class XlprDb(Connection):
         h = render_echart_html('cpu_memory', body='<br/>'.join(htmltexts))
         return h
 
-    def dbview_disk_memory(self, recent=datetime.timedelta(days=30), date_trunc='day'):
+    def dbview_disk_memory(self, recent=datetime.timedelta(days=360), date_trunc='day'):
         """ 查看disk硬盘使用近况
         """
         from pyxllib.data.echarts import render_echart_html

{pyxllib-0.3.128 → pyxllib-0.3.130}/pyxllib/ext/yuquelib.py

@@ -20,10 +20,10 @@ class Yuque:
     语雀请求限制：每小时最多 5000 次请求，每秒最多 100 次请求
     """
 
-    def __init__(self, token, user_id=None):
+    def __init__(self, token=None, user_id=None):
         self.base_url = "https://www.yuque.com/api/v2"
         self.headers = {
-            "X-Auth-Token": token,
+            "X-Auth-Token": token or os.environ.get('YUQUE_TOKEN'),
             "Content-Type": "application/json"
         }
         self._user_id = user_id

{pyxllib-0.3.128 → pyxllib-0.3.130}/pyxllib/file/pupil.py

@@ -140,7 +140,7 @@ def gen_file_filter(s):
 
 
 def getfiles(root, filter_rule=None):
-    """对os.walk进一步封装，返回所有匹配的文件
+    r""" 对os.walk进一步封装，返回所有匹配的文件
 
     可以这样遍历一个目录下的所有文件：
     for f in getfiles(r'C:\pycode\code4101py', r'.py'):

{pyxllib-0.3.128 → pyxllib-0.3.130}/pyxllib/file/specialist/filelib.py

@@ -923,7 +923,7 @@ class XlPath(type(pathlib.Path())):
                 res.add(p.relative_to(self).as_posix())
         return res
 
-    def relpath(self, ref_dir) -> str:
+    def relpath(self, ref_dir) -> 'XlPath':
         r""" 当前路径，相对于ref_dir的路径位置
 
         >>> File('C:/a/b/c.txt').relpath('C:/a/')

{pyxllib-0.3.128 → pyxllib-0.3.130}/pyxllib/file/xlsxlib.py

@@ -766,7 +766,7 @@ class XlCell(openpyxl.cell.cell.Cell):  # 适用于 openpyxl.cell.cell.MergedCel
         # openpyxl的机制，如果没有配置日期格式，读取到的是默认的'mm-dd-yy'，其实在中文场景，默认格式应该是后者
         if fmt == 'mm-dd-yy':
             return 'yyyy/m/d'  # 中文的默认日期格式
-        elif fmt == 'yyyy\-mm\-dd':  # 不知道为什么会有提取到这种\的情况，先暴力替换了
+        elif fmt == r'yyyy\-mm\-dd':  # 不知道为什么会有提取到这种\的情况，先暴力替换了
             fmt = 'yyyy-mm-dd'
         return fmt